Tasks in CLEF-IP 2013

  • Passage retrieval starting from claims (patentability or novelty search) : The topics in this task will be based on the claims in patent application documents. Given a claim, the participants will be asked to retrieve relevant documents in the collection and mark out the relevant passages in these documents.
    This task is very similar to the one organized in 2012. As background data for the topics, data that can be used in query generation, participants will be given patent documents that are members of the patent family claims' application document.

    More on this task is available on the task's page, further detailed information can be found here.

  • Text to image/image to text : Given a patent application document - as an XML file - and the set of images occurring in the application, extract the links between the image labels and the text pointing to the object of the image label.

  • Structure Recognition Task : The topics in this third task are patent images representing flow-charts. Participants in this task will be asked to extract the information in these images and return it in a predefined textual format.
    The task is similar to the one organized in 2012. This year we added images with more challenging cases of flow-charts, namely those containing metanodes.